Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 3034 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.9532. Min Act: -0.1700

Data Index: 1294976 (Open Web Text)

Max Activating Token Index: 592

Text #1

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.8074. Min Act: -0.1700

Data Index: 3972607 (Open Web Text)

Max Activating Token Index: 518

Text #2

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.7778. Min Act: -0.1700

Data Index: 2660223 (Open Web Text)

Max Activating Token Index: 523

Text #3

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.7710. Min Act: -0.1700

Data Index: 7093129 (Open Web Text)

Max Activating Token Index: 673

Text #4

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.7738. Min Act: -0.1700

Data Index: 6540401 (Open Web Text)

Max Activating Token Index: 699

Text #5

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.7083. Min Act: -0.1700

Data Index: 1208437 (Open Web Text)

Max Activating Token Index: 111

Text #6

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.7202. Min Act: -0.1700

Data Index: 2322979 (Open Web Text)

Max Activating Token Index: 441

Text #7

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.6987. Min Act: -0.1700

Data Index: 2793226 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.7106. Min Act: -0.1700

Data Index: 2831832 (Open Web Text)

Max Activating Token Index: 611

Text #9

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.6892. Min Act: -0.1700

Data Index: 5976736 (Open Web Text)

Max Activating Token Index: 839

Text #10

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.6686. Min Act: -0.1700

Data Index: 8636868 (Open Web Text)

Max Activating Token Index: 527

Text #11

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.6861. Min Act: -0.1700

Data Index: 8247070 (Open Web Text)

Max Activating Token Index: 236

Text #12

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.6665. Min Act: -0.1700

Data Index: 8636869 (Open Web Text)

Max Activating Token Index: 141

Text #13

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.6614. Min Act: -0.1700

Data Index: 5130651 (Open Web Text)

Max Activating Token Index: 654

Text #14

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.6569. Min Act: -0.1700

Data Index: 3988933 (Open Web Text)

Max Activating Token Index: 715

Text #15

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.6367. Min Act: -0.1700

Data Index: 7091074 (Open Web Text)

Max Activating Token Index: 700

Text #16

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.6441. Min Act: -0.1700

Data Index: 1348897 (Open Web Text)

Max Activating Token Index: 611

Text #17

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.6530. Min Act: -0.1700

Data Index: 3245473 (Open Web Text)

Max Activating Token Index: 768

Text #18

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.6612. Min Act: -0.1700

Data Index: 4898252 (Open Web Text)

Max Activating Token Index: 885

Text #19

Max Range: 3.9532. Min Range: -3.9532

Max Act: 3.6231. Min Act: -0.1700

Data Index: 6982418 (Open Web Text)

Max Activating Token Index: 912